USING MIXTURE, MULTI-PROCESS, AND OTHER MULTI-DIMENSIONAL IRT MODELS TO ACCOUNT FOR EXTREME AND MIDPOINT RESPONSE STYLE USE IN PERSONALITY ASSESSMENTLucci, Michael (2017) USING MIXTURE, MULTI-PROCESS, AND OTHER MULTI-DIMENSIONAL IRT MODELS TO ACCOUNT FOR EXTREME AND MIDPOINT RESPONSE STYLE USE IN PERSONALITY ASSESSMENT. Doctoral Dissertation, University of Pittsburgh. (Unpublished)
AbstractThe validity of interpreting questionnaire results is threatened by the possible overuse of extreme and midpoint response options. Since respondents may view the response options in different ways, accounting for midpoint (MRS) and extreme response style (ERS) use is important for accurate estimation of the latent trait. Biased sum scores provide poor trait estimates for two people with the same latent trait yet different response styles. With the categorical view of response styles, respondents are seen as having a certain response style or not and are classified into different groups. The mixture graded response and mixture partial credit models were compared in this study. With the continuous view of response styles, respondents are seen as having varying degrees of different response style traits. A multidimensional model estimates substantive and response style trait levels for each person. A Multi-process model (M-PM) was used in this study to break down the response process into two and three subprocesses used in completing a five point Likert scale. The Multidimensional Partial Credit (MPCM) and Multidimensional Nominal Response (MNRM) models with substantive and response style scoring functions were also explored. This study used an existing data set to investigate how the five different IRT models for addressing ERS and MRS performed for three different personality subscales (Anxiety, Openness to Experience Feelings, and Compliance) from the German version of Costa and McCrae’s NEO Personality Inventory-Revised. Each subscale illustrated different relationships with and uses of ERS and MRS traits. The response process traits of the M-PM differed from response style traits of the other models. The two and three class mixture models, the two and three dimensional MNRM and MPCM, and the two process model for intensity ERS and direction fit better than standard IRT models. ERS accounted for more item response variability than MRS. The MPCM is suggested to account for ERS and MRS due to the number of estimated parameters and amount of explained variability in item responses. The results are compared with each other and to results from a previous study. Limitations of this study and ideas for future research are presented. Share
Details
MetricsMonthly Views for the past 3 yearsPlum AnalyticsActions (login required)
|
![[feed]](/images/feed-icon-32x32.png){kind=icon}